AutoSGD runs three parallel SGD streams at nearby learning rates, uses paired noisy objective estimates to pick the winner, and is claimed to converge with little user tuning.
Julia: A fresh approach to numerical computing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
AutoSGD runs three parallel SGD streams at nearby learning rates, uses paired noisy objective estimates to pick the winner, and is claimed to converge with little user tuning.